AI-driven medical images for prediction and classification breast cancer by using convolutional neural networks

Breast cancer is a common disease that many women face throughout their lives. Therefore, early diagnosis is the most effective and reliable tool for effectively treating cancer. Computer-aided diagnosis is one of the software technologies designed to assist doctors in detecting or diagnose cancer. In fact, to reduce mortality via using medical images analysis with less time. Recently, medical images analysis used convolutional neural networks to evaluate a vast amount of data for detecting cancer cells images classification. However, breast cancer tumors could be determined by analyzing microscopic images. Analysis taken a complex time consuming. So, there are many risks like misdiagnosis absent from pathologists. On this study our goals refer to assign and   reduce the time-consuming for classification process. Fore to increase the accuracy when they attempt using data augmentation for to evaluate the performance of the classifiers, by using various performance metrics. Furthermore, in  this study, the pre-trained convolution neural network (CNNs) models are applied to extract the features that Support Vector Machine (SVM), to classify and transfer learning from pre-trained CNN models for feature extraction and classification, this approach was applied to image-based breast cancer classification using histopathological images from the public dataset, and the experimental result shown that the resent50achieved high accuracy and 97.2%has been compared to the inceptionV3with accuracy of96.6%.Finally, on this study we focusing to recommends expanding to research other diseases such as Pneumonia, Brain Cancer, Covid-19, etc. Therefore, to incorporate other classifier, such as BayesNet, Decision Tree, etc., for to achieve higher classification accuracy by using different type of others models.